Papers

Reproduction of AdEx dynamics on neuromorphic hardware through data embedding and simulation-based inference

J Huhle, J Kaiser, E Müller, J Schemmel - arXiv preprint arXiv:2412.02437, 2024 - arxiv.org
Computer Science paper cs.NE Suggest

… model emulated on the BrainScaleS-2 neuromorphic system, and subsequently leverage sequential neural posterior estimation (SNPE), a simulation-based inference …

Link to paper

BibTeX

@article{2412.02437v1,
Author        = {Jakob Huhle and Jakob Kaiser and Eric Müller and Johannes Schemmel},
Title         = {Reproduction of AdEx dynamics on neuromorphic hardware through data
  embedding and simulation-based inference},
Eprint        = {2412.02437v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {cs.NE},
Abstract      = {The development of mechanistic models of physical systems is essential for
understanding their behavior and formulating predictions that can be validated
experimentally. Calibration of these models, especially for complex systems,
requires automated optimization methods due to the impracticality of manual
parameter tuning. In this study, we use an autoencoder to automatically extract
relevant features from the membrane trace of a complex neuron model emulated on
the BrainScaleS-2 neuromorphic system, and subsequently leverage sequential
neural posterior estimation (SNPE), a simulation-based inference algorithm, to
approximate the posterior distribution of neuron parameters. Our results
demonstrate that the autoencoder is able to extract essential features from the
observed membrane traces, with which the SNPE algorithm is able to find an
approximation of the posterior distribution. This suggests that the combination
of an autoencoder with the SNPE algorithm is a promising optimization method
for complex systems.},
Year          = {2024},
Month         = {Dec},
Url           = {http://arxiv.org/abs/2412.02437v1},
File          = {2412.02437v1.pdf}
}

Share